返回列表
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks
国外 · 纸上电台 · 发布于 2026-10-01 · 0 次阅读
来源:arXiv cs.AI · 2026-10-01 · 新型 AI / 新品发布
arXiv:2609.38288v1 Announce Type: new Abstract: We present AREX-2, an effort to advance the self-improving capability of LLM agents, which we define as the ability to iteratively refine a solution at
本条资讯由「纸上电台」整理自 arXiv cs.AI,仅作交流参考,版权归原作者所有。

